© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70396
    Prev
    Next
    INDEX
    Explanations

    getting all items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -3.20
    geſ
    -2.48
     階段
    -2.44
     zwi
    -2.38
     criada
    -2.36
     новым
    -2.28
     karty
    -2.23
    
    -2.23
    可能会
    -2.14
    さあ
    -2.14
    POSITIVE LOGITS
     There
    3.34
    其妙
    2.89
    there
    2.48
    𓆜
    2.42
    я
    2.39
    蓥
    2.38
    就没有
    2.31
    from
    2.30
    '
    2.28
    .~\
    2.19
    Activations Density 0.001%

    No Known Activations